Model fitting using partially ranked data

Abstract

The importance of models for complete ranking data is well-established in the literature. Partial rankings, on the other hand, arise naturally when the set of objects to be ranked is relatively large. Partial rankings give rise to classes of compatible order preserving complete rankings. In this article, we define an exponential model for complete rankings and calibrate it on the basis of a random sample of partial rankings data. We appeal to the EM algorithm. The approach is illustrated in some simulations and in real data.

Keywords:

• Mallows exponential model
• incomplete rankings
• compatibility
• EM algorithm

Data Availability Statement

Data openly available in a public repository that issues datasets with DOIs.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Correction Statement

This article has been corrected with minor changes. These changes do not impact the academic content of the article.

Additional information

Funding

The research was partially supported by Natural Sciences and Engineering Research Council of Canada [grant number OGP0009068].